Skip to content

Expose temperature parameter on TTS client #486

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rchoyhughes merged 2 commits into from
May 21, 2026
Merged

Expose temperature parameter on TTS client #486

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2c430b0
Expose temperature parameter on high-level TTS client
rchoyhughes May 21, 2026
e1d7bb3
bump version to 0.13.13
rchoyhughes May 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ dynamic = ["version"]

[tool.poetry]
name = "hume"
version = "0.13.12"
version = "0.13.13"
description = "A Python SDK for Hume AI"
readme = "README.md"
authors = []
Expand Down
40 changes: 40 additions & 0 deletions src/hume/tts/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,7 @@ def synthesize_json(
num_generations: typing.Optional[int] = OMIT,
split_utterances: typing.Optional[bool] = OMIT,
strip_headers: typing.Optional[bool] = OMIT,
temperature: typing.Optional[float] = OMIT,
version: typing.Optional[OctaveVersion] = OMIT,
instant_mode: typing.Optional[bool] = OMIT,
request_options: typing.Optional[RequestOptions] = None,
Expand Down Expand Up @@ -94,6 +95,9 @@ def synthesize_json(
strip_headers : typing.Optional[bool]
If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).

temperature : typing.Optional[float]
Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.

version : typing.Optional[OctaveVersion]
Selects the Octave model version used to synthesize speech for this request. If you omit this field, Hume automatically routes the request to the most appropriate model. Setting a specific version ensures stable and repeatable behavior across requests.

Expand Down Expand Up @@ -146,6 +150,7 @@ def synthesize_json(
num_generations=num_generations,
split_utterances=split_utterances,
strip_headers=strip_headers,
temperature=temperature,
version=version,
instant_mode=instant_mode,
request_options=request_options,
Expand All @@ -162,6 +167,7 @@ def synthesize_file(
num_generations: typing.Optional[int] = OMIT,
split_utterances: typing.Optional[bool] = OMIT,
strip_headers: typing.Optional[bool] = OMIT,
temperature: typing.Optional[float] = OMIT,
version: typing.Optional[OctaveVersion] = OMIT,
instant_mode: typing.Optional[bool] = OMIT,
request_options: typing.Optional[RequestOptions] = None,
Expand Down Expand Up @@ -204,6 +210,9 @@ def synthesize_file(
strip_headers : typing.Optional[bool]
If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).

temperature : typing.Optional[float]
Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.

version : typing.Optional[OctaveVersion]
Selects the Octave model version used to synthesize speech for this request. If you omit this field, Hume automatically routes the request to the most appropriate model. Setting a specific version ensures stable and repeatable behavior across requests.

Expand Down Expand Up @@ -251,6 +260,7 @@ def synthesize_file(
num_generations=num_generations,
split_utterances=split_utterances,
strip_headers=strip_headers,
temperature=temperature,
version=version,
instant_mode=instant_mode,
request_options=request_options,
Expand All @@ -267,6 +277,7 @@ def synthesize_file_streaming(
num_generations: typing.Optional[int] = OMIT,
split_utterances: typing.Optional[bool] = OMIT,
strip_headers: typing.Optional[bool] = OMIT,
temperature: typing.Optional[float] = OMIT,
version: typing.Optional[OctaveVersion] = OMIT,
instant_mode: typing.Optional[bool] = OMIT,
request_options: typing.Optional[RequestOptions] = None,
Expand Down Expand Up @@ -307,6 +318,9 @@ def synthesize_file_streaming(
strip_headers : typing.Optional[bool]
If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).

temperature : typing.Optional[float]
Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.

version : typing.Optional[OctaveVersion]
Selects the Octave model version used to synthesize speech for this request. If you omit this field, Hume automatically routes the request to the most appropriate model. Setting a specific version ensures stable and repeatable behavior across requests.

Expand Down Expand Up @@ -352,6 +366,7 @@ def synthesize_file_streaming(
num_generations=num_generations,
split_utterances=split_utterances,
strip_headers=strip_headers,
temperature=temperature,
version=version,
instant_mode=instant_mode,
request_options=request_options,
Expand All @@ -368,6 +383,7 @@ def synthesize_json_streaming(
num_generations: typing.Optional[int] = OMIT,
split_utterances: typing.Optional[bool] = OMIT,
strip_headers: typing.Optional[bool] = OMIT,
temperature: typing.Optional[float] = OMIT,
version: typing.Optional[OctaveVersion] = OMIT,
instant_mode: typing.Optional[bool] = OMIT,
request_options: typing.Optional[RequestOptions] = None,
Expand Down Expand Up @@ -410,6 +426,9 @@ def synthesize_json_streaming(
strip_headers : typing.Optional[bool]
If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).

temperature : typing.Optional[float]
Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.

version : typing.Optional[OctaveVersion]
Selects the Octave model version used to synthesize speech for this request. If you omit this field, Hume automatically routes the request to the most appropriate model. Setting a specific version ensures stable and repeatable behavior across requests.

Expand Down Expand Up @@ -457,6 +476,7 @@ def synthesize_json_streaming(
num_generations=num_generations,
split_utterances=split_utterances,
strip_headers=strip_headers,
temperature=temperature,
version=version,
instant_mode=instant_mode,
request_options=request_options,
Expand Down Expand Up @@ -619,6 +639,7 @@ async def synthesize_json(
num_generations: typing.Optional[int] = OMIT,
split_utterances: typing.Optional[bool] = OMIT,
strip_headers: typing.Optional[bool] = OMIT,
temperature: typing.Optional[float] = OMIT,
version: typing.Optional[OctaveVersion] = OMIT,
instant_mode: typing.Optional[bool] = OMIT,
request_options: typing.Optional[RequestOptions] = None,
Expand Down Expand Up @@ -661,6 +682,9 @@ async def synthesize_json(
strip_headers : typing.Optional[bool]
If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).

temperature : typing.Optional[float]
Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.

version : typing.Optional[OctaveVersion]
Selects the Octave model version used to synthesize speech for this request. If you omit this field, Hume automatically routes the request to the most appropriate model. Setting a specific version ensures stable and repeatable behavior across requests.

Expand Down Expand Up @@ -721,6 +745,7 @@ async def main() -> None:
num_generations=num_generations,
split_utterances=split_utterances,
strip_headers=strip_headers,
temperature=temperature,
version=version,
instant_mode=instant_mode,
request_options=request_options,
Expand All @@ -737,6 +762,7 @@ async def synthesize_file(
num_generations: typing.Optional[int] = OMIT,
split_utterances: typing.Optional[bool] = OMIT,
strip_headers: typing.Optional[bool] = OMIT,
temperature: typing.Optional[float] = OMIT,
version: typing.Optional[OctaveVersion] = OMIT,
instant_mode: typing.Optional[bool] = OMIT,
request_options: typing.Optional[RequestOptions] = None,
Expand Down Expand Up @@ -779,6 +805,9 @@ async def synthesize_file(
strip_headers : typing.Optional[bool]
If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).

temperature : typing.Optional[float]
Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.

version : typing.Optional[OctaveVersion]
Selects the Octave model version used to synthesize speech for this request. If you omit this field, Hume automatically routes the request to the most appropriate model. Setting a specific version ensures stable and repeatable behavior across requests.

Expand Down Expand Up @@ -834,6 +863,7 @@ async def main() -> None:
num_generations=num_generations,
split_utterances=split_utterances,
strip_headers=strip_headers,
temperature=temperature,
version=version,
instant_mode=instant_mode,
request_options=request_options,
Expand All @@ -851,6 +881,7 @@ async def synthesize_file_streaming(
num_generations: typing.Optional[int] = OMIT,
split_utterances: typing.Optional[bool] = OMIT,
strip_headers: typing.Optional[bool] = OMIT,
temperature: typing.Optional[float] = OMIT,
version: typing.Optional[OctaveVersion] = OMIT,
instant_mode: typing.Optional[bool] = OMIT,
request_options: typing.Optional[RequestOptions] = None,
Expand Down Expand Up @@ -891,6 +922,9 @@ async def synthesize_file_streaming(
strip_headers : typing.Optional[bool]
If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).

temperature : typing.Optional[float]
Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.

version : typing.Optional[OctaveVersion]
Selects the Octave model version used to synthesize speech for this request. If you omit this field, Hume automatically routes the request to the most appropriate model. Setting a specific version ensures stable and repeatable behavior across requests.

Expand Down Expand Up @@ -944,6 +978,7 @@ async def main() -> None:
num_generations=num_generations,
split_utterances=split_utterances,
strip_headers=strip_headers,
temperature=temperature,
version=version,
instant_mode=instant_mode,
request_options=request_options,
Expand All @@ -961,6 +996,7 @@ async def synthesize_json_streaming(
num_generations: typing.Optional[int] = OMIT,
split_utterances: typing.Optional[bool] = OMIT,
strip_headers: typing.Optional[bool] = OMIT,
temperature: typing.Optional[float] = OMIT,
version: typing.Optional[OctaveVersion] = OMIT,
instant_mode: typing.Optional[bool] = OMIT,
request_options: typing.Optional[RequestOptions] = None,
Expand Down Expand Up @@ -1003,6 +1039,9 @@ async def synthesize_json_streaming(
strip_headers : typing.Optional[bool]
If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).

temperature : typing.Optional[float]
Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.

version : typing.Optional[OctaveVersion]
Selects the Octave model version used to synthesize speech for this request. If you omit this field, Hume automatically routes the request to the most appropriate model. Setting a specific version ensures stable and repeatable behavior across requests.

Expand Down Expand Up @@ -1058,6 +1097,7 @@ async def main() -> None:
num_generations=num_generations,
split_utterances=split_utterances,
strip_headers=strip_headers,
temperature=temperature,
version=version,
instant_mode=instant_mode,
request_options=request_options,
Expand Down
Loading